Training in progress, step 650

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e13dcdfac1567edf8d0a35ab9a0e69e13e4d4a2cfa4f7ec4382db67e5ebafc0b
+oid sha256:426151b36cec917b14a15214973ed502f8ea33ed6fcfede1e67ed989a36bb672
 size 25200088

trainer_log.jsonl

@@ -70,3 +70,9 @@
 {"current_steps": 590, "total_steps": 1500, "loss": 0.2774, "accuracy": 0.862500011920929, "learning_rate": 3.3221666168464584e-06, "epoch": 0.47628657921291623, "percentage": 39.33, "elapsed_time": "1:22:39", "remaining_time": "2:07:29", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 600, "total_steps": 1500, "loss": 0.3082, "accuracy": 0.9375, "learning_rate": 3.272542485937369e-06, "epoch": 0.4843592330978809, "percentage": 40.0, "elapsed_time": "1:23:54", "remaining_time": "2:05:52", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 600, "total_steps": 1500, "eval_loss": 0.2698034942150116, "epoch": 0.4843592330978809, "percentage": 40.0, "elapsed_time": "1:24:24", "remaining_time": "2:06:37", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 610, "total_steps": 1500, "loss": 0.267, "accuracy": 0.8500000238418579, "learning_rate": 3.222579492361179e-06, "epoch": 0.4924318869828456, "percentage": 40.67, "elapsed_time": "1:25:49", "remaining_time": "2:05:12", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 620, "total_steps": 1500, "loss": 0.2849, "accuracy": 0.887499988079071, "learning_rate": 3.1722995515381644e-06, "epoch": 0.5005045408678103, "percentage": 41.33, "elapsed_time": "1:27:11", "remaining_time": "2:03:44", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 630, "total_steps": 1500, "loss": 0.2448, "accuracy": 0.887499988079071, "learning_rate": 3.121724717912138e-06, "epoch": 0.508577194752775, "percentage": 42.0, "elapsed_time": "1:28:30", "remaining_time": "2:02:13", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 640, "total_steps": 1500, "loss": 0.2505, "accuracy": 0.8999999761581421, "learning_rate": 3.0708771752766397e-06, "epoch": 0.5166498486377397, "percentage": 42.67, "elapsed_time": "1:29:43", "remaining_time": "2:00:33", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 650, "total_steps": 1500, "loss": 0.2889, "accuracy": 0.9125000238418579, "learning_rate": 3.019779227044398e-06, "epoch": 0.5247225025227044, "percentage": 43.33, "elapsed_time": "1:30:57", "remaining_time": "1:58:56", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 650, "total_steps": 1500, "eval_loss": 0.2533933222293854, "epoch": 0.5247225025227044, "percentage": 43.33, "elapsed_time": "1:31:27", "remaining_time": "1:59:36", "throughput": "0.00", "total_tokens": 0}